{"id":"https://openalex.org/W4412888948","doi":"https://doi.org/10.18653/v1/2025.findings-acl.67","title":"Nuclear Deployed!: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents","display_name":"Nuclear Deployed!: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888948","doi":"https://doi.org/10.18653/v1/2025.findings-acl.67"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.67","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.67","pdf_url":"https://aclanthology.org/2025.findings-acl.67.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.67.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101586109","display_name":"Rufeng Xu","orcid":"https://orcid.org/0000-0003-0688-1980"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongwu Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100679806","display_name":"Xiaojian Li","orcid":"https://orcid.org/0000-0002-3175-7810"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaojian Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366893","display_name":"Shuo Chen","orcid":"https://orcid.org/0009-0009-9503-4265"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuo Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102545026","display_name":"Wei Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1226","last_page":"1310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.8719000220298767,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.8719000220298767,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.868399977684021,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5930951833724976},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.47787442803382874},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3294488191604614},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.3244101405143738},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19474530220031738},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.17354139685630798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5930951833724976},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.47787442803382874},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3294488191604614},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.3244101405143738},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19474530220031738},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.17354139685630798}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.67","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.67","pdf_url":"https://aclanthology.org/2025.findings-acl.67.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.67","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.67","pdf_url":"https://aclanthology.org/2025.findings-acl.67.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6700000166893005,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G366789873","display_name":null,"funder_award_id":"62176135","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7422017672","display_name":null,"funder_award_id":"U2268202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888948.pdf","grobid_xml":"https://content.openalex.org/works/W4412888948.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"evolving":[5],"into":[6],"autonomous":[7,124],"decision-makers,":[8],"raising":[9],"concerns":[10],"about":[11],"catastrophic":[12,84,121],"risks":[13,31,122],"in":[14,18,83,123],"high-stakes":[15],"scenarios,":[16],"particularly":[17],"Chemical,":[19],"Biological,":[20],"Radiological":[21],"and":[22,41,58,74,86,110],"Nuclear":[23],"(CBRN)":[24],"domains.Based":[25],"on":[26],"the":[27,37,113,118],"insight":[28],"that":[29,77,104],"such":[30,61],"can":[32,80,107],"originate":[33],"from":[34],"trade-offs":[35],"between":[36],"agent's":[38],"Helpful,":[39],"Harmlessness":[40],"Honest":[42],"(HHH)":[43],"goals,":[44],"we":[45,115],"build":[46],"a":[47],"novel":[48],"three-stage":[49],"evaluation":[50],"framework,":[51],"which":[52],"is":[53],"carefully":[54],"constructed":[55],"to":[56,130],"effectively":[57],"naturally":[59],"expose":[60],"risks.We":[62,101],"conduct":[63],"14,400":[64],"agentic":[65],"simulations":[66],"across":[67],"12":[68],"advanced":[69],"LLMs,":[70],"with":[71],"extensive":[72],"experiments":[73],"analysis.Results":[75],"reveal":[76],"LLM":[78,125],"agents":[79,106],"autonomously":[81],"engage":[82],"behaviors":[85],"deception,":[87],"without":[88],"being":[89],"deliberately":[90],"induced.Furthermore,":[91],"stronger":[92],"reasoning":[93],"abilities":[94],"often":[95],"increase,":[96],"rather":[97],"than":[98],"mitigate,":[99],"these":[100,105],"also":[102],"show":[103],"violate":[108],"instructions":[109],"superior":[111],"commands.On":[112],"whole,":[114],"empirically":[116],"prove":[117],"existence":[119],"of":[120],"agents.We":[126],"release":[127],"our":[128],"code":[129],"foster":[131],"further":[132],"research.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
